Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    popular things or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ร
    0.59
    ל
    0.55
    an
    0.55
    ב
    0.53
    ก
    0.53
    EC
    0.52
    J
    0.52
    ft
    0.51
    yr
    0.51
    January
    0.50
    POSITIVE LOGITS
     populer
    0.89
     popular
    0.86
     populares
    0.85
     populaires
    0.84
     популяр
    0.84
     populaire
    0.79
     लोकप्रिय
    0.79
     জনপ্রিয়তা
    0.76
    popular
    0.76
     beliebt
    0.74
    Act Density 0.046%

    No Known Activations